SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Opensource CAL 3D printer with configuration flexibility based on commercially available optical components and 3D printed components. Intended for research purposes.

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

Standard Open Arm 100

Official repository for "SO-101 Bench: Measuring the Gap Between Semantic and Geometric Competence in Robot Foundation Models"

Codebase intelligence for TypeScript and JavaScript. Free static layer: unused code, duplication, circular deps, complexity hotspots, architecture boundaries. Optional paid runtime layer: hot-path …

Durable, Distributed runtime for ALL of your agents - OpenAI, ADK, Langchain, Vercel, etc.

A vector index built on TurboQuant, written in Rust with Python bindings

[ICLR 2026] LiTo: Surface Light Field Tokenization

🇫🇷 Skills pour agents IA spécialisés dans la bureaucratie française : Comptable, Notaire, ...

Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

Project Lyra: Open Generative 3D World Models

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

DFlash: Block Diffusion for Flash Speculative Decoding

A very fast geospatial point clustering library for browsers and Node.

Official implementation of 2Xplat: Two Experts Are Better Than One Generalist

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)

Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

ArtCraft is an intentional crafting engine for artists, designers, and filmmakers

The open-source AI voice studio. Clone, dictate, create.

[CVPR 2026 Highlight] tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction

bitmap to vector graphics converter

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and te…

[ICML 2026 Oral] Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence

Dreame lawn mower integration for Home Assistant

[ICML 2026] WorldMirror: Fast and Universal 3D reconstruction model for versatile tasks

Depth Anything 3